SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networksby Serdar ErisenFirst…
Using Large Language Model for End-to-End Chinese ASR and NERby Yuang Li, Jiawei Yu, Min…
Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgeryby Beilei Cui, Mobarakol…
Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstractsby Zihao…
Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognitionby Damien…
Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responsesby Hui Liu, Shikai JinFirst…
MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognitionby Peihao Xiang, Kaida Wu, Chaohao Lin,…
FOR: Finetuning for Object Level Open Vocabulary Image Retrievalby Hila Levi, Guy Heller, Dan LeviFirst…
Deliberation in Latent Space via Differentiable Cache Augmentationby Luyang Liu, Jonas Pfeiffer, Jiaxing Wu, Jun…
The Dynamic Duo of Collaborative Masking and Target for Advanced Masked Autoencoder Learningby Shentong MoFirst…